totally-not-an-llm
commited on
Commit
•
d74a4a8
1
Parent(s):
7c7b1d1
Update README.md
Browse files
README.md
CHANGED
@@ -9,13 +9,13 @@ license: llama2
|
|
9 |
<figcaption style="font-size: 1em;"><i>"super cute baby alpaca laying on a cloud", Model: epicrealism_pureEvolutionV3</i></figcaption>
|
10 |
</figure>
|
11 |
|
12 |
-
***
|
13 |
-
Disclaimer: The model might have a tokenizer issue, but functions. Updates to come.
|
14 |
-
***
|
15 |
-
|
16 |
AlpacaCielo-13b is a llama-2 based model designed for creative tasks, such as storytelling and roleplay, while still doing well with other chatbot purposes. It is a triple model merge of Nous-Hermes + Guanaco + Storywriter. While it is mostly *"uncensored"*, it still inherits some alignment from Guanaco.
|
17 |
|
18 |
-
|
|
|
|
|
|
|
|
|
19 |
|
20 |
```
|
21 |
### Human: {prompt}
|
|
|
9 |
<figcaption style="font-size: 1em;"><i>"super cute baby alpaca laying on a cloud", Model: epicrealism_pureEvolutionV3</i></figcaption>
|
10 |
</figure>
|
11 |
|
|
|
|
|
|
|
|
|
12 |
AlpacaCielo-13b is a llama-2 based model designed for creative tasks, such as storytelling and roleplay, while still doing well with other chatbot purposes. It is a triple model merge of Nous-Hermes + Guanaco + Storywriter. While it is mostly *"uncensored"*, it still inherits some alignment from Guanaco.
|
13 |
|
14 |
+
[GPTQ quants](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ)<br>
|
15 |
+
[GGML quants](https://huggingface.co/TheBloke/AlpacaCielo-13B-GGML)<br>
|
16 |
+
(Courtesy of TheBloke)
|
17 |
+
|
18 |
+
**Prompt format is this (Guanaco QLORA in oobabooga):**
|
19 |
|
20 |
```
|
21 |
### Human: {prompt}
|